Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words related to technology or computing

    oai_token-act-pair · gpt-3.5-turbo

    short, high-frequency words and syllables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Meow
    -0.61
     Chocobo
    -0.60
     Mara
    -0.60
    rals
    -0.60
     Fitness
    -0.59
     Haram
    -0.58
    FactoryReloaded
    -0.58
    yip
    -0.57
    nai
    -0.57
    shi
    -0.57
    POSITIVE LOGITS
    bert
    0.75
    ymes
    0.74
    ç·
    0.66
     veins
    0.65
    closure
    0.63
    etary
    0.60
    Clear
    0.60
    ertodd
    0.60
     Fors
    0.58
     thereof
    0.58
    Act Density 0.372%

    No Known Activations